The application of Artificial Intelligence in banks in the context of the three lines of defence model

Tammenga, Alette

doi:10.5117/mab.94.47158

Cited by 8 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence (AI) has emerged as a powerful tool for fraud detection, offering advanced analytics capabilities and real-time monitoring to identify suspicious activities (Singla and Jangir, 2020). However, the adoption of AI-driven fraud detection systems presents several challenges and considerations that organizations must address to maximize their effectiveness and mitigate potential risks as explained in figure 3 (Tammenga, 2020). (Tammenga, 2020) Data quality and availability are fundamental challenges in AI-driven fraud detection.…”

Section: Challenges and Considerations In Ai-driven Fraud Detectionmentioning

confidence: 99%

Enhancing fraud detection in accounting through AI: Techniques and case studies

Beatrice Oyinkansola Adelakun,

Ebere Ruth Onwubuariri,

Gbenga Adeniyi Adeniran

et al. 2024

Financ. account. res. j.

View full text Add to dashboard Cite

The integration of artificial intelligence (AI) into accounting has significantly transformed the landscape of fraud detection. Traditional methods, while effective to some extent, often struggle with the increasing complexity and volume of financial data. AI, with its advanced analytical capabilities, offers a promising solution to these challenges. This review provides an overview of the techniques used in AI-driven fraud detection in accounting and highlights case studies that demonstrate the practical applications and benefits of these technologies. AI techniques for fraud detection in accounting primarily involve machine learning (ML), natural language processing (NLP), and data mining. Machine learning algorithms, such as supervised and unsupervised learning models, are employed to identify patterns and anomalies in financial data that could indicate fraudulent activity. Supervised learning involves training a model on a labelled dataset containing examples of both fraudulent and non-fraudulent transactions, enabling the model to learn the distinguishing features of fraud. Unsupervised learning, on the other hand, is used to detect anomalies without prior labeling, identifying outliers that deviate from the norm. Natural language processing (NLP) is utilized to analyze textual data, such as emails and financial documents, to uncover suspicious activities and hidden relationships. This is particularly useful in forensic accounting, where vast amounts of unstructured data must be examined for signs of fraud. Data mining techniques are also critical, enabling the extraction of useful information from large datasets and the identification of trends and patterns that may not be immediately apparent. Several case studies illustrate the effectiveness of AI in enhancing fraud detection in accounting. One notable example is the use of AI by major financial institutions to combat credit card fraud. By implementing ML algorithms, these institutions have significantly improved their ability to detect fraudulent transactions in real-time. The algorithms analyze transaction patterns and flag those that deviate from a customer's typical behavior, allowing for immediate investigation and action. Another case study involves a large multinational corporation that integrated NLP and data mining techniques into its internal audit processes. The company utilized AI to analyze thousands of financial documents and emails, uncovering a complex fraud scheme that had previously gone undetected. The AI system identified unusual communication patterns and financial discrepancies, leading to a comprehensive investigation and the eventual prosecution of the perpetrators. A further example is found in the public sector, where government agencies have employed AI to detect and prevent procurement fraud. By analyzing historical procurement data, AI systems can identify anomalies and potential red flags, such as unusually high bids or frequent contract awards to the same vendor. This proactive approach has enabled these agencies to save millions of dollars and improve the transparency and integrity of their procurement processes. The application of AI in fraud detection within accounting represents a significant advancement over traditional methods. Techniques such as machine learning, natural language processing, and data mining offer powerful tools for identifying and mitigating fraudulent activities. The case studies discussed highlight the practical benefits and successes achieved through AI-driven fraud detection, demonstrating its potential to enhance the accuracy, efficiency, and effectiveness of fraud prevention efforts. As the complexity and volume of financial transactions continue to grow, the role of AI in fraud detection will become increasingly vital. Continued advancements in AI technology, coupled with its integration into accounting practices, promise to further strengthen the fight against financial fraud, safeguarding the integrity of financial systems and promoting trust and confidence among stakeholders. Keywords: Fraud, Detection, Accounting, Artificial Intelligence, Case Studies.

show abstract

Section: Challenges and Considerations In Ai-driven Fraud Detectionmentioning

confidence: 99%

Enhancing fraud detection in accounting through AI: Techniques and case studies

Beatrice Oyinkansola Adelakun,

Ebere Ruth Onwubuariri,

Gbenga Adeniyi Adeniran

et al. 2024

Financ. account. res. j.

View full text Add to dashboard Cite

show abstract

“…Its accuracy has been demonstrated in a number of areas, including education, criminality, and health [5], and the banking industry is no different. Therefore, AI and ML techniques are increasingly used in the banking industry [6]. In this sense, companies are increasingly looking to use AI to gain benefits, driven by the availability of substantial amounts of data and by growing computing power.…”

Section: Introductionmentioning

confidence: 99%

Financial revolution: a systemic analysis of artificial intelligence and machine learning in the banking sector

Jáuregui-Velarde,

Andrade-Arenas,

Molina-Velarde

et al. 2024

IJECE

View full text Add to dashboard Cite

This paper reviews the advances, challenges, and approaches of artificial intelligence (AI) and machine learning (ML) in the banking sector. The use of these technologies is accelerating in various industries, including banking. However, the literature on banking is scattered, making a global understanding difficult. This study reviewed the main approaches in terms of applications and algorithmic models, as well as the benefits and challenges associated with their implementation in banking, in addition to a bibliometric analysis of variables related to the distribution of publications and the most productive countries, as well as an analysis of the co-occurrence and dynamics of keywords. Following the preferred reporting items for systematic reviews and meta-analyses (PRISMA) framework, forty articles were selected for review. The results indicate that these technologies are used in the banking sector for customer segmentation, credit risk analysis, recommendation, and fraud detection. It should be noted that credit analysis and fraud detection are the most implemented areas, using algorithms such as random forests (RF), decision trees (DT), support vector machines (SVM), and logistic regression (LR), among others. In addition, their use brings significant benefits for decision-making and optimizing banking operations. However, the handling of substantial amounts of data with these technologies poses ethical challenges.

show abstract

“…Both frameworks provide general guidance and they have been modified to meet the specific requirements of many sectors-for example, central banks (Luburić 2017), commercial banks Adm. Sci. 2024, 14, 83 2 of 13 (Minto and Arndorfer 2015;Borg et al 2020), and Islamic financial institutions (Hakim 2017)-and business processes, such as quality management (Luburić et al 2015), the use of artificial intelligence in banks (Tammenga 2020), andESG (IIA andWBCSD 2022). Similarly, TLM could provide a solid basis for the governance of whistleblowing.…”

Section: Introductionmentioning

confidence: 99%

Whistleblowing Based on the Three Lines Model

Kagias,

Garefalakis,

Passas

et al. 2024

Administrative Sciences

View full text Add to dashboard Cite

Directive 1937/2019 on the protection of persons who report breaches of Union law became effective very recently. However, Directive 1937/2019 lacks sufficient guidance on the implementation or governance of whistleblowing frameworks. In addition, the existing literature lacks a definition of whistleblowing and whistleblowing frameworks that is appropriate for internal audit and fraud prevention. The purpose of this paper is to address the lack of a definition of whistleblowing and whistleblowing framework appropriate for internal auditing and to guide the roles and responsibilities within an organization to apply and maintain a robust whistleblowing framework. To this effect, the Three Lines Model is used, one of the most recognized theoretical models in effective risk governance and internal audit.

show abstract

The application of Artificial Intelligence in banks in the context of the three lines of defence model

Cited by 8 publications

References 12 publications

Enhancing fraud detection in accounting through AI: Techniques and case studies

Enhancing fraud detection in accounting through AI: Techniques and case studies

Financial revolution: a systemic analysis of artificial intelligence and machine learning in the banking sector

Whistleblowing Based on the Three Lines Model

Contact Info

Product

Resources

About